analiza aiqbench
RepoLaunch addresses a critical bottleneck in automated software engineering by using agentic frameworks to handle cross-language builds and testing, achieving a 78% success rate that significantly outperforms existing Python/Linux-only systems. This open-source tool enables fully automated SWE dataset creation, reducing human intervention to the initial task-design stage and accelerating benchmarking workflows. Its adoption by multiple recent works highlights its immediate utility for scaling agentic evaluation and training pipelines.
RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms
arXiv:2603.05026v2 Announce Type: replace-cross Abstract: Language model (LM) agents have driven substantial progress in automated software engineering (SWE), yet building and testing software repositories at scale remains a largely manual and labor-intensive bottleneck. In this work, we introduce RepoLaunch, a novel agentic framework that automatically resolves dependencies, compiles source code, and extracts test results across diverse programming languages and operating systems. RepoLaunch achieves a 78% build success rate, outperforming the Python/Linux-only prior system by 18%. To demonstrate its application, we further present a fully automated pipeline for SWE dataset creation driven by RepoLaunch, which only requires human input at the task-design stage. RepoLaunch is open-sourced, and its automated task-generation pipeline has already been adopted by several recent works on agentic benchmarking and training.
Abstract:Language model (LM) agents have driven substantial progress in automated software engineering (SWE), yet building and testing software repositories at scale remains a largely manual and labor-intensive bottleneck. In this work, we introduce RepoLaunch, a novel agentic framework that automatically resolves dependencies, compiles source code, and extracts test results across diverse programming languages and operating systems. RepoLaunch achieves a 78% build success rate, outperforming the Python/Linux-only prior system by 18%. To demonstrate its application, we further present a fully automated pipeline for SWE dataset creation driven by RepoLaunch, which only requires human input at the task-design stage. RepoLaunch is open-sourced, and its automated task-generation pipeline has already been adopted by several recent works on agentic benchmarking and training.
Under peer review. 22 pages, 5 figures, 9 tables
Software Engineering (cs.SE); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
arXiv:2603.05026 [cs.SE]
(or arXiv:2603.05026v2 [cs.SE] for this version)
Text integral sub licența deschisă a publicației · 144 cuvinte
Subiecte conexe
RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms
arXiv · 6 oct. 2026
A Candid Abacus AI Review: The All-in-One AI Platform for Professionals & Enterprises
KDnuggets · 10 sept. 2026
From code to diagrams: Agentic architecture documentation with Amazon Bedrock AgentCore
AWS · 2 sept. 2026
AgentOps: Operationalize agentic AI at scale with Amazon Bedrock AgentCore
AWS · 1 iun. 2026